End of training
Browse files- .gitattributes +1 -0
- README.md +68 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scaler.pt +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-3000/unet/config.json +73 -0
- checkpoint-3000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-4000/optimizer.bin +3 -0
- checkpoint-4000/random_states_0.pkl +3 -0
- checkpoint-4000/scaler.pt +3 -0
- checkpoint-4000/scheduler.bin +3 -0
- checkpoint-4000/unet/config.json +73 -0
- checkpoint-4000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-5000/optimizer.bin +3 -0
- checkpoint-5000/random_states_0.pkl +3 -0
- checkpoint-5000/scaler.pt +3 -0
- checkpoint-5000/scheduler.bin +3 -0
- checkpoint-5000/unet/config.json +73 -0
- checkpoint-5000/unet/diffusion_pytorch_model.safetensors +3 -0
- feature_extractor/preprocessor_config.json +27 -0
- logs/text2image-fine-tune/1767299243.525676/events.out.tfevents.1767299243.admin---AgriEdgeX-Research.3517659.1 +3 -0
- logs/text2image-fine-tune/1767299243.5278287/hparams.yml +56 -0
- logs/text2image-fine-tune/events.out.tfevents.1767299241.admin---AgriEdgeX-Research.3517659.0 +3 -0
- model_index.json +38 -0
- scheduler/scheduler_config.json +15 -0
- text_encoder/config.json +24 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +13 -0
- unet/config.json +73 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +38 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
- val_imgs_grid.png +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
val_imgs_grid.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Manojb/stable-diffusion-2-1-base
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
license: creativeml-openrail-m
|
| 5 |
+
inference: true
|
| 6 |
+
tags:
|
| 7 |
+
- stable-diffusion
|
| 8 |
+
- stable-diffusion-diffusers
|
| 9 |
+
- text-to-image
|
| 10 |
+
- diffusers
|
| 11 |
+
- diffusers-training
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
# Text-to-image finetuning - ButterChicken98/soy_qwen_bact_v2
|
| 19 |
+
|
| 20 |
+
This pipeline was finetuned from **Manojb/stable-diffusion-2-1-base** on the **ButterChicken98/soyabean_bact_puls_plus_healthy_Qwen_Detailed** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A photo of a soybean leaf with Early stage Bacterial Pustule, showing small, yellowish-brown lesions with a water-soaked appearance.']:
|
| 21 |
+
|
| 22 |
+

|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
## Pipeline usage
|
| 26 |
+
|
| 27 |
+
You can use the pipeline like so:
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from diffusers import DiffusionPipeline
|
| 31 |
+
import torch
|
| 32 |
+
|
| 33 |
+
pipeline = DiffusionPipeline.from_pretrained("ButterChicken98/soy_qwen_bact_v2", torch_dtype=torch.float16)
|
| 34 |
+
prompt = "A photo of a soybean leaf with Early stage Bacterial Pustule, showing small, yellowish-brown lesions with a water-soaked appearance."
|
| 35 |
+
image = pipeline(prompt).images[0]
|
| 36 |
+
image.save("my_image.png")
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
## Training info
|
| 40 |
+
|
| 41 |
+
These are the key hyperparameters used during training:
|
| 42 |
+
|
| 43 |
+
* Epochs: 29
|
| 44 |
+
* Learning rate: 1e-05
|
| 45 |
+
* Batch size: 8
|
| 46 |
+
* Gradient accumulation steps: 1
|
| 47 |
+
* Image resolution: 512
|
| 48 |
+
* Mixed-precision: fp16
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/butterchicken-iit-indore/text2image-fine-tune/runs/hvt7i83s).
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
## Intended uses & limitations
|
| 55 |
+
|
| 56 |
+
#### How to use
|
| 57 |
+
|
| 58 |
+
```python
|
| 59 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
#### Limitations and bias
|
| 63 |
+
|
| 64 |
+
[TODO: provide examples of latent issues and potential remediations]
|
| 65 |
+
|
| 66 |
+
## Training details
|
| 67 |
+
|
| 68 |
+
[TODO: describe the data used to train the model]
|
checkpoint-3000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:339ea56bf79bbca0359e0feff308a7c5b25362ae504c6e997c742ad5fb9549d0
|
| 3 |
+
size 6927874725
|
checkpoint-3000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ae39dd55574172a5329e9ed65a683188d0ef5add1e3bf15075a4472349a57b2
|
| 3 |
+
size 14821
|
checkpoint-3000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
|
| 3 |
+
size 1383
|
checkpoint-3000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d02e9f17ce277518998a9e4d19ad84caf30db9f1d981277dab1d182ec06d87f2
|
| 3 |
+
size 1401
|
checkpoint-3000/unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"_name_or_path": "Manojb/stable-diffusion-2-1-base",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20,
|
| 13 |
+
20
|
| 14 |
+
],
|
| 15 |
+
"attention_type": "default",
|
| 16 |
+
"block_out_channels": [
|
| 17 |
+
320,
|
| 18 |
+
640,
|
| 19 |
+
1280,
|
| 20 |
+
1280
|
| 21 |
+
],
|
| 22 |
+
"center_input_sample": false,
|
| 23 |
+
"class_embed_type": null,
|
| 24 |
+
"class_embeddings_concat": false,
|
| 25 |
+
"conv_in_kernel": 3,
|
| 26 |
+
"conv_out_kernel": 3,
|
| 27 |
+
"cross_attention_dim": 1024,
|
| 28 |
+
"cross_attention_norm": null,
|
| 29 |
+
"down_block_types": [
|
| 30 |
+
"CrossAttnDownBlock2D",
|
| 31 |
+
"CrossAttnDownBlock2D",
|
| 32 |
+
"CrossAttnDownBlock2D",
|
| 33 |
+
"DownBlock2D"
|
| 34 |
+
],
|
| 35 |
+
"downsample_padding": 1,
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"dual_cross_attention": false,
|
| 38 |
+
"encoder_hid_dim": null,
|
| 39 |
+
"encoder_hid_dim_type": null,
|
| 40 |
+
"flip_sin_to_cos": true,
|
| 41 |
+
"freq_shift": 0,
|
| 42 |
+
"in_channels": 4,
|
| 43 |
+
"layers_per_block": 2,
|
| 44 |
+
"mid_block_only_cross_attention": null,
|
| 45 |
+
"mid_block_scale_factor": 1,
|
| 46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 47 |
+
"norm_eps": 1e-05,
|
| 48 |
+
"norm_num_groups": 32,
|
| 49 |
+
"num_attention_heads": null,
|
| 50 |
+
"num_class_embeds": null,
|
| 51 |
+
"only_cross_attention": false,
|
| 52 |
+
"out_channels": 4,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 64,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
checkpoint-3000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f303d38fc8abef9f80601d8d50738e799c6e9673dfa129bf5858e427af43ffc
|
| 3 |
+
size 3463726504
|
checkpoint-4000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c5d1f6b7b482003ebc4a3a581458a4d7898795c495523762167c4ab2dd5b270
|
| 3 |
+
size 6927874725
|
checkpoint-4000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abb05fff1b89e04cc159117a7b00e433cd80b292b3c2ddbf25b6bd9e5cbf7263
|
| 3 |
+
size 14821
|
checkpoint-4000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
|
| 3 |
+
size 1383
|
checkpoint-4000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abf8d991cc0a7bf66ce6dd76db8fbcf166033896cb31e5e3f7ee7309f6bc1759
|
| 3 |
+
size 1401
|
checkpoint-4000/unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"_name_or_path": "Manojb/stable-diffusion-2-1-base",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20,
|
| 13 |
+
20
|
| 14 |
+
],
|
| 15 |
+
"attention_type": "default",
|
| 16 |
+
"block_out_channels": [
|
| 17 |
+
320,
|
| 18 |
+
640,
|
| 19 |
+
1280,
|
| 20 |
+
1280
|
| 21 |
+
],
|
| 22 |
+
"center_input_sample": false,
|
| 23 |
+
"class_embed_type": null,
|
| 24 |
+
"class_embeddings_concat": false,
|
| 25 |
+
"conv_in_kernel": 3,
|
| 26 |
+
"conv_out_kernel": 3,
|
| 27 |
+
"cross_attention_dim": 1024,
|
| 28 |
+
"cross_attention_norm": null,
|
| 29 |
+
"down_block_types": [
|
| 30 |
+
"CrossAttnDownBlock2D",
|
| 31 |
+
"CrossAttnDownBlock2D",
|
| 32 |
+
"CrossAttnDownBlock2D",
|
| 33 |
+
"DownBlock2D"
|
| 34 |
+
],
|
| 35 |
+
"downsample_padding": 1,
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"dual_cross_attention": false,
|
| 38 |
+
"encoder_hid_dim": null,
|
| 39 |
+
"encoder_hid_dim_type": null,
|
| 40 |
+
"flip_sin_to_cos": true,
|
| 41 |
+
"freq_shift": 0,
|
| 42 |
+
"in_channels": 4,
|
| 43 |
+
"layers_per_block": 2,
|
| 44 |
+
"mid_block_only_cross_attention": null,
|
| 45 |
+
"mid_block_scale_factor": 1,
|
| 46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 47 |
+
"norm_eps": 1e-05,
|
| 48 |
+
"norm_num_groups": 32,
|
| 49 |
+
"num_attention_heads": null,
|
| 50 |
+
"num_class_embeds": null,
|
| 51 |
+
"only_cross_attention": false,
|
| 52 |
+
"out_channels": 4,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 64,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
checkpoint-4000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e18c1f47ea4e993f3db8481ff0d14a762ccef06af898f0382b3be7e7af3ec6aa
|
| 3 |
+
size 3463726504
|
checkpoint-5000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63dca9573730fee7398bc40fc33abdb9f35d8004c62cbfa4d9301e6594b65996
|
| 3 |
+
size 6927874725
|
checkpoint-5000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cf4288fc2d93334c275b3406bc28c3a3d003db9471d68ce24a33cb0ca5b35a9
|
| 3 |
+
size 14821
|
checkpoint-5000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
|
| 3 |
+
size 1383
|
checkpoint-5000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff8089318ecef721d068a0f7d4d2d22bd54d376566c7d530413da298438031bd
|
| 3 |
+
size 1401
|
checkpoint-5000/unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"_name_or_path": "Manojb/stable-diffusion-2-1-base",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20,
|
| 13 |
+
20
|
| 14 |
+
],
|
| 15 |
+
"attention_type": "default",
|
| 16 |
+
"block_out_channels": [
|
| 17 |
+
320,
|
| 18 |
+
640,
|
| 19 |
+
1280,
|
| 20 |
+
1280
|
| 21 |
+
],
|
| 22 |
+
"center_input_sample": false,
|
| 23 |
+
"class_embed_type": null,
|
| 24 |
+
"class_embeddings_concat": false,
|
| 25 |
+
"conv_in_kernel": 3,
|
| 26 |
+
"conv_out_kernel": 3,
|
| 27 |
+
"cross_attention_dim": 1024,
|
| 28 |
+
"cross_attention_norm": null,
|
| 29 |
+
"down_block_types": [
|
| 30 |
+
"CrossAttnDownBlock2D",
|
| 31 |
+
"CrossAttnDownBlock2D",
|
| 32 |
+
"CrossAttnDownBlock2D",
|
| 33 |
+
"DownBlock2D"
|
| 34 |
+
],
|
| 35 |
+
"downsample_padding": 1,
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"dual_cross_attention": false,
|
| 38 |
+
"encoder_hid_dim": null,
|
| 39 |
+
"encoder_hid_dim_type": null,
|
| 40 |
+
"flip_sin_to_cos": true,
|
| 41 |
+
"freq_shift": 0,
|
| 42 |
+
"in_channels": 4,
|
| 43 |
+
"layers_per_block": 2,
|
| 44 |
+
"mid_block_only_cross_attention": null,
|
| 45 |
+
"mid_block_scale_factor": 1,
|
| 46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 47 |
+
"norm_eps": 1e-05,
|
| 48 |
+
"norm_num_groups": 32,
|
| 49 |
+
"num_attention_heads": null,
|
| 50 |
+
"num_class_embeds": null,
|
| 51 |
+
"only_cross_attention": false,
|
| 52 |
+
"out_channels": 4,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 64,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
checkpoint-5000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f300063de8fcd9e9b36595bc7b7cdfa55b1094b8adc44667dc13f96e76a71f1e
|
| 3 |
+
size 3463726504
|
feature_extractor/preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 224
|
| 26 |
+
}
|
| 27 |
+
}
|
logs/text2image-fine-tune/1767299243.525676/events.out.tfevents.1767299243.admin---AgriEdgeX-Research.3517659.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d07e3d823f20fe9455c02119d179878e56d21c43e1be6eb5be86961afd34fd5
|
| 3 |
+
size 2846
|
logs/text2image-fine-tune/1767299243.5278287/hparams.yml
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: true
|
| 9 |
+
checkpointing_steps: 1000
|
| 10 |
+
checkpoints_total_limit: 3
|
| 11 |
+
dataloader_num_workers: 8
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: ButterChicken98/soyabean_bact_puls_plus_healthy_Qwen_Detailed
|
| 14 |
+
dream_detail_preservation: 1.0
|
| 15 |
+
dream_training: false
|
| 16 |
+
enable_xformers_memory_efficient_attention: false
|
| 17 |
+
foreach_ema: false
|
| 18 |
+
gradient_accumulation_steps: 1
|
| 19 |
+
gradient_checkpointing: false
|
| 20 |
+
hub_model_id: soy_qwen_bact_v2
|
| 21 |
+
hub_token: null
|
| 22 |
+
image_column: image
|
| 23 |
+
image_interpolation_mode: lanczos
|
| 24 |
+
input_perturbation: 0
|
| 25 |
+
learning_rate: 1.0e-05
|
| 26 |
+
local_rank: -1
|
| 27 |
+
logging_dir: logs
|
| 28 |
+
lr_scheduler: cosine
|
| 29 |
+
lr_warmup_steps: 500
|
| 30 |
+
max_grad_norm: 1.0
|
| 31 |
+
max_train_samples: null
|
| 32 |
+
max_train_steps: 5000
|
| 33 |
+
mixed_precision: fp16
|
| 34 |
+
noise_offset: 0.1
|
| 35 |
+
non_ema_revision: null
|
| 36 |
+
num_train_epochs: 29
|
| 37 |
+
offload_ema: false
|
| 38 |
+
output_dir: /home/svashistha/diffusion/output/soy_qwen/v1/bact
|
| 39 |
+
prediction_type: null
|
| 40 |
+
pretrained_model_name_or_path: Manojb/stable-diffusion-2-1-base
|
| 41 |
+
push_to_hub: true
|
| 42 |
+
random_flip: true
|
| 43 |
+
report_to: all
|
| 44 |
+
resolution: 512
|
| 45 |
+
resume_from_checkpoint: latest
|
| 46 |
+
revision: null
|
| 47 |
+
scale_lr: false
|
| 48 |
+
seed: 42
|
| 49 |
+
snr_gamma: 5.0
|
| 50 |
+
tracker_project_name: text2image-fine-tune
|
| 51 |
+
train_batch_size: 8
|
| 52 |
+
train_data_dir: null
|
| 53 |
+
use_8bit_adam: false
|
| 54 |
+
use_ema: false
|
| 55 |
+
validation_epochs: 5
|
| 56 |
+
variant: null
|
logs/text2image-fine-tune/events.out.tfevents.1767299241.admin---AgriEdgeX-Research.3517659.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:535aec3a395fd57f1c2385e455caeef05ca31a007d57ec8eafe2e2873ed1b273
|
| 3 |
+
size 2453577
|
model_index.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableDiffusionPipeline",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"_name_or_path": "Manojb/stable-diffusion-2-1-base",
|
| 5 |
+
"feature_extractor": [
|
| 6 |
+
"transformers",
|
| 7 |
+
"CLIPImageProcessor"
|
| 8 |
+
],
|
| 9 |
+
"image_encoder": [
|
| 10 |
+
null,
|
| 11 |
+
null
|
| 12 |
+
],
|
| 13 |
+
"requires_safety_checker": false,
|
| 14 |
+
"safety_checker": [
|
| 15 |
+
null,
|
| 16 |
+
null
|
| 17 |
+
],
|
| 18 |
+
"scheduler": [
|
| 19 |
+
"diffusers",
|
| 20 |
+
"PNDMScheduler"
|
| 21 |
+
],
|
| 22 |
+
"text_encoder": [
|
| 23 |
+
"transformers",
|
| 24 |
+
"CLIPTextModel"
|
| 25 |
+
],
|
| 26 |
+
"tokenizer": [
|
| 27 |
+
"transformers",
|
| 28 |
+
"CLIPTokenizer"
|
| 29 |
+
],
|
| 30 |
+
"unet": [
|
| 31 |
+
"diffusers",
|
| 32 |
+
"UNet2DConditionModel"
|
| 33 |
+
],
|
| 34 |
+
"vae": [
|
| 35 |
+
"diffusers",
|
| 36 |
+
"AutoencoderKL"
|
| 37 |
+
]
|
| 38 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "PNDMScheduler",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"beta_end": 0.012,
|
| 5 |
+
"beta_schedule": "scaled_linear",
|
| 6 |
+
"beta_start": 0.00085,
|
| 7 |
+
"clip_sample": false,
|
| 8 |
+
"num_train_timesteps": 1000,
|
| 9 |
+
"prediction_type": "epsilon",
|
| 10 |
+
"set_alpha_to_one": false,
|
| 11 |
+
"skip_prk_steps": true,
|
| 12 |
+
"steps_offset": 1,
|
| 13 |
+
"timestep_spacing": "leading",
|
| 14 |
+
"trained_betas": null
|
| 15 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPTextModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"dtype": "float16",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 23,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 512,
|
| 22 |
+
"transformers_version": "5.0.0.dev0",
|
| 23 |
+
"vocab_size": 49408
|
| 24 |
+
}
|
text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
|
| 3 |
+
size 680820392
|
tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|startoftext|>",
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"model_max_length": 77,
|
| 10 |
+
"pad_token": "!",
|
| 11 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"_name_or_path": "Manojb/stable-diffusion-2-1-base",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20,
|
| 13 |
+
20
|
| 14 |
+
],
|
| 15 |
+
"attention_type": "default",
|
| 16 |
+
"block_out_channels": [
|
| 17 |
+
320,
|
| 18 |
+
640,
|
| 19 |
+
1280,
|
| 20 |
+
1280
|
| 21 |
+
],
|
| 22 |
+
"center_input_sample": false,
|
| 23 |
+
"class_embed_type": null,
|
| 24 |
+
"class_embeddings_concat": false,
|
| 25 |
+
"conv_in_kernel": 3,
|
| 26 |
+
"conv_out_kernel": 3,
|
| 27 |
+
"cross_attention_dim": 1024,
|
| 28 |
+
"cross_attention_norm": null,
|
| 29 |
+
"down_block_types": [
|
| 30 |
+
"CrossAttnDownBlock2D",
|
| 31 |
+
"CrossAttnDownBlock2D",
|
| 32 |
+
"CrossAttnDownBlock2D",
|
| 33 |
+
"DownBlock2D"
|
| 34 |
+
],
|
| 35 |
+
"downsample_padding": 1,
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"dual_cross_attention": false,
|
| 38 |
+
"encoder_hid_dim": null,
|
| 39 |
+
"encoder_hid_dim_type": null,
|
| 40 |
+
"flip_sin_to_cos": true,
|
| 41 |
+
"freq_shift": 0,
|
| 42 |
+
"in_channels": 4,
|
| 43 |
+
"layers_per_block": 2,
|
| 44 |
+
"mid_block_only_cross_attention": null,
|
| 45 |
+
"mid_block_scale_factor": 1,
|
| 46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 47 |
+
"norm_eps": 1e-05,
|
| 48 |
+
"norm_num_groups": 32,
|
| 49 |
+
"num_attention_heads": null,
|
| 50 |
+
"num_class_embeds": null,
|
| 51 |
+
"only_cross_attention": false,
|
| 52 |
+
"out_channels": 4,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 64,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f300063de8fcd9e9b36595bc7b7cdfa55b1094b8adc44667dc13f96e76a71f1e
|
| 3 |
+
size 3463726504
|
vae/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"_name_or_path": "Manojb/stable-diffusion-2-1-base",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
128,
|
| 8 |
+
256,
|
| 9 |
+
512,
|
| 10 |
+
512
|
| 11 |
+
],
|
| 12 |
+
"down_block_types": [
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D",
|
| 16 |
+
"DownEncoderBlock2D"
|
| 17 |
+
],
|
| 18 |
+
"force_upcast": true,
|
| 19 |
+
"in_channels": 3,
|
| 20 |
+
"latent_channels": 4,
|
| 21 |
+
"latents_mean": null,
|
| 22 |
+
"latents_std": null,
|
| 23 |
+
"layers_per_block": 2,
|
| 24 |
+
"mid_block_add_attention": true,
|
| 25 |
+
"norm_num_groups": 32,
|
| 26 |
+
"out_channels": 3,
|
| 27 |
+
"sample_size": 768,
|
| 28 |
+
"scaling_factor": 0.18215,
|
| 29 |
+
"shift_factor": null,
|
| 30 |
+
"up_block_types": [
|
| 31 |
+
"UpDecoderBlock2D",
|
| 32 |
+
"UpDecoderBlock2D",
|
| 33 |
+
"UpDecoderBlock2D",
|
| 34 |
+
"UpDecoderBlock2D"
|
| 35 |
+
],
|
| 36 |
+
"use_post_quant_conv": true,
|
| 37 |
+
"use_quant_conv": true
|
| 38 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
|
| 3 |
+
size 167335342
|
val_imgs_grid.png
ADDED
|
Git LFS Details
|